Chengyu Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chengyu Zheng has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Mingqiang Wei
Nanjing University of Aeronautics and Astronautics, Nanjing, China
2 shared publications Ding Shi
Nanjing University of Aeronautics and Astronautics Nanjing China
1 shared publicationDong Liang
Nanjing University of Aeronautics and Astronautics Nanjing China
1 shared publication- Haoran Xie
Lingnan University, Tuen Mun, Hong Kong
1 shared publication - Honghua Chen
School of Data Science, Lingnan University, Hong Kong, China
1 shared publication Mengjiao Ma
School of Computer Science and Technology, NanJing University of Aeronautics and Astronautics, NanJing, China
1 shared publication
Latest Publications
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
RegiFormer: Unsupervised Point Cloud Registration via Geometric Local-to-Global Transformer and Self-Augmentation
Representation learning on two but partial point clouds remains an open challenge in unsupervised point cloud registration (U-PCR). In this paper, we introduce RegiFormer, a geometric local-to-global transformer-based unsupervised framework equipped with a self-augmentation strategy, for point cloud registration. The geometric local-to-global transformer aggregates features not only from local neighborhoods but also extracts global intra-relationships within the entire point cloud using a transformation-invariant geometry embedding. Additionally, it enhances the inter-relationships between paired point clouds. To overcome the limited ability of U-PCR methods to learn alignment knowledge, we design a self-augmentation strategy that can be flexibly integrated into advanced models, significantly boosting their registration performance. Extensive experiments, conducted on five popular synthetic and real-scanned benchmarks, demonstrate the superior performance of RegiFormer when compared to state-of-the-art methods, both qualitatively and quantitatively.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
RegiFormer: Unsupervised Point Cloud Registration via Geometric Local-to-Global Transformer and Self-Augmentation
Representation learning on two but partial point clouds remains an open challenge in unsupervised point cloud registration (U-PCR). In this paper, we introduce RegiFormer, a geometric local-to-global transformer-based unsupervised framework equipped with a self-augmentation strategy, for point cloud registration. The geometric local-to-global transformer aggregates features not only from local neighborhoods but also extracts global intra-relationships within the entire point cloud using a transformation-invariant geometry embedding. Additionally, it enhances the inter-relationships between paired point clouds. To overcome the limited ability of U-PCR methods to learn alignment knowledge, we design a self-augmentation strategy that can be flexibly integrated into advanced models, significantly boosting their registration performance. Extensive experiments, conducted on five popular synthetic and real-scanned benchmarks, demonstrate the superior performance of RegiFormer when compared to state-of-the-art methods, both qualitatively and quantitatively.
- 8 January 2022
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (1) , 377-388
GlassNet: Label Decoupling‐based Three‐stream Neural Network for Robust Image Glass Detection
- 8 January 2022
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (1) , 377-388
GlassNet: Label Decoupling‐based Three‐stream Neural Network for Robust Image Glass Detection